@inproceedings{ko-etal-2025-dense,
    title = "When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using {G}rad{N}orm{IR}",
    author = "Ko, Dayoon  and
      Kim, Jinyoung  and
      Kim, Sohyeon  and
      Kim, Jinhyuk  and
      Lee, Jaehoon  and
      Song, Seonghak  and
      Lee, Minyoung  and
      Kim, Gunhee",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.1334/",
    pages = "25977--25996",
    ISBN = "979-8-89176-256-5",
    abstract = "Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval systems. In this paper, we propose a novel task of predicting whether a corpus is out-of-distribution (OOD) relative to a dense retriever before indexing. Addressing this task allows us to proactively manage retriever updates, preventing potential retrieval failures. We introduce GradNormIR, an unsupervised approach that leverages gradient norms to detect OOD corpora effectively. Experiments on the BEIR benchmark demonstrate that GradNormIR enables timely updates of dense retrievers in evolving document collections, significantly enhancing retrieval robustness and efficiency."
}